Curates 341k SATD items from 1k Apache repos, analyzes effort differences by debt type, and shows BERT/TextCNN models predict repayment effort from text better than traditional ML baselines.
Identifying self-admitted technical debt in issue tracking systems using machine learning.Empirical Software Engineering.2022;27(6)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2023 2verdicts
UNVERDICTED 2representative citing papers
A systematic literature review summarizing the shift in SATD detection from heuristic keyword methods to ML, DL, and Transformer models, along with performance trends and open challenges like dataset heterogeneity.
citing papers explorer
-
Text Tells the Cost: Predicting and Analyzing Repayment Effort of Self-Admitted Technical Debt
Curates 341k SATD items from 1k Apache repos, analyzes effort differences by debt type, and shows BERT/TextCNN models predict repayment effort from text better than traditional ML baselines.
-
Self-Admitted Technical Debt Detection Approaches: A Decade Systematic Review
A systematic literature review summarizing the shift in SATD detection from heuristic keyword methods to ML, DL, and Transformer models, along with performance trends and open challenges like dataset heterogeneity.